public float ClassificationThreshold { get; set; }
To filter out false positive results and still get variety in matched
natural language inputs for your agent, you can tune the machine learning
classification threshold. If the returned score value is less than the
threshold value, then a no-match event will be triggered. The score values
range from 0.0 (completely uncertain) to 1.0 (completely certain). If set
to 0.0, the default of 0.3 is used.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-04-09 UTC."],[[["This webpage provides documentation for the `NluSettings` class within the Google Cloud Dialogflow CX v3 API, specifically in version 2.16.0."],["The `NluSettings` class is part of the `Google.Cloud.Dialogflow.Cx.V3` namespace and is used to manage settings related to Natural Language Understanding (NLU)."],["It includes properties to configure the machine learning classification threshold, indicated by `ClassificationThreshold` which ranges from 0.0 to 1.0."],["The documentation details the available properties `ModelTrainingMode` and `ModelType` which allow the user to specify the NLU model's training mode and model type, respectively."],["This document also provides a list of previous versions of `NluSettings` ranging from version 2.23.0 (latest) down to version 1.0.0, all accessible through respective links."]]],[]]
